Noometry

Model comparison

Claude Sonnet 4.5 vs Gemini 2.5 Pro

Claude Sonnet 4.5 and Gemini 2.5 Pro score almost the same on the Noometry Index (44.1 vs 45.0), so choose on price, context window or the category you care about most.

Last verified . 61 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Summary

  • They share 61 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 3 categories and Gemini 2.5 Pro in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 45.2.
  • The biggest single-benchmark swing is ARC-AGI-1: 63.7% for Claude Sonnet 4.5 and 41% for Gemini 2.5 Pro.
  • Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Sonnet 4.5Gemini 2.5 Pro
ProviderAnthropicGoogle
Noometry Index44.145.0
Released2025-09-292025-03-25
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K66K
Input $ / M tokens$3$1.25
Output $ / M tokens$15$10
Results tracked7378

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Gemini 2.5 Pro: 42.4 (#101)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
SWE-bench Verified71.3%57.6%
SWE-bench Verified (bash only)71.4%53.6%
LMArena WebDev13931227
SciCode44.7%42.8%
GSO14.7%3.9%
WeirdML47.7%54%
LMArena Coding14891452
ALE-Bench796.15785.52
AlgoTune1.521.51
Aider Polyglot—83.1%
SWE-bench Multilingual67%—
LiveBench Coding—85.9%
CadEval—64%

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Gemini 2.5 Pro: 29.2 (#88)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
Terminal-Bench46.5%32.6%
GDPval42.5%23.3%
Remote Labor Index2.1%0.8%
τ²-bench Banking25.3%13.7%
DeepResearch Bench52.6%42.8%
LMArena Search11591142
METR Time Horizons67.4%55.4%
Vending-Bench 23,839573.64
Berkeley Function Calling Leaderboard73.2%—
TheAgentCompany—30.3%
τ²-bench Airline72%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
OSWorld62.9%—
BALROG—43.3%

Reasoning Gemini 2.5 Pro leads

Claude Sonnet 4.5: 26.9 (#125), Gemini 2.5 Pro: 28.8 (#99)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
ARC-AGI-213.6%4.9%
SimpleBench54.3%62.4%
Kagi LLM Benchmark57.9%70.3%
ARC-AGI-163.7%41%
CritPt1.1%2%
Chess Puzzles12%20%
EnigmaEval6%5.6%
LMArena Hard Prompts14621455
DTBench83.2%82.4%
LMCA38.8%34.8%
Epoch Capabilities Index146.84145.32
ForecastBench61.961.3
NYT Connections (extended)37.3%—
EBR-Bench2.4%—
LiveBench Reasoning—89.8%
Mystery Game Puzzles17%—
LiveBench Data Analysis—79.9%
LiveBench—82.3%

Math Too close to call

Claude Sonnet 4.5: 32.3 (#216), Gemini 2.5 Pro: 32.5 (#213)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
FrontierMath (Tiers 1-3)23.9%24.6%
FrontierMath Tier 42.4%0%
OTIS Mock AIME 2024-202577.8%84.7%
Omni-MATH55.3%41.6%
LMArena Math14491450
MATH Level 597.7%95.9%
FrontierMath (Feb 2025 set)15.2%14.1%
FrontierMath Tier 4 (v1)4.2%4.2%
ProofBench19%—
LiveBench Math—90.2%

Knowledge Gemini 2.5 Pro leads

Claude Sonnet 4.5: 48.4 (#76), Gemini 2.5 Pro: 56.0 (#46)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
GPQA Diamond82.3%85.3%
Humanity's Last Exam13.7%21.6%
MMLU-Pro86.9%86.3%
Vectara Hallucination Rate12%7%
GPQA (HELM)68.6%74.9%
LMArena Expert14821452
SimpleQA Verified30.7%—
Confabulations—10.6%

Multimodal Gemini 2.5 Pro leads

Claude Sonnet 4.5: 34.8 (#89), Gemini 2.5 Pro: 45.2 (#18)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
VPCT39.8%48%
LMArena Document14501421
LMArena Vision—1263
GeoBench—86%
SpatialViz-Bench—44.7%

Multilingual Gemini 2.5 Pro leads

Claude Sonnet 4.5: 53.4 (#69), Gemini 2.5 Pro: 55.3 (#31)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
LMArena Non-English14251451
LMArena Chinese14591507
LMArena French14581472
LMArena German14271487
LMArena Japanese13901461
LMArena Korean14031434
LMArena Russian14371461
LMArena Spanish14571473

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), Gemini 2.5 Pro: 75.0 (#75)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
IFEval85%84%
LMArena Instruction Following14591437
LiveBench Instruction Following—80.6%

Long Context Gemini 2.5 Pro leads

Claude Sonnet 4.5: 45.2 (#46), Gemini 2.5 Pro: 59.8 (#5)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
LMArena Longer Query14761449
Fiction.LiveBench—91.7%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Gemini 2.5 Pro: 63.7 (#62)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Pro
LMArena Text14391458
LMArena Creative Writing14421454
EQ-Bench Creative Writing16781421
WildBench85.4%85.7%
LMArena Multi-Turn14651453
Short-Story Creative Writing—83.8%
LiveBench Language—67.8%

Frequently asked questions

Is Claude Sonnet 4.5 better than Gemini 2.5 Pro?

Claude Sonnet 4.5 and Gemini 2.5 Pro score almost the same on the Noometry Index (44.1 vs 45.0), so choose on price, context window or the category you care about most.

Which is cheaper, Claude Sonnet 4.5 or Gemini 2.5 Pro?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Gemini 2.5 Pro better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and Gemini 2.5 Pro share?

61 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 2.5 Pro has 78.

Related comparisons

Go deeper